Machine learning on Azure for baseball decision analysis
What-if analysis is a great use case for Azure machine intelligence techniques. Bart Czernicki, Principal Technical Architect with the Microsoft Machine Intelligence team, shows you how in his sample web app for baseball decision analysis based on ML.NET and Blazor called the Machine Learning Workbench. He shows you an example architecture on Azure and provides all the source code on GitHub.
Bart has created the Machine Learning Workbench as a web app with a friendly interface to a powerful what-if analysis engine. It takes historical and current baseball data and uses AI and machine learning models to make informed predictions.
The solution delivers National Baseball Hall of Fame insights, but the architectural approach applies to decision analysis systems in general, from building a fantasy baseball team to forecasting financial scenarios for budgeting and planning.
The Machine Learning Workbench is built in ASP.NET core using ML.NET, an open-source framework that provides the inference engine, and Blazor Server to render the interface. Azure SignalR Service brokers communications between Workbench and the user interface.
Machine Learning Workbench architecture on Azure
Published on:
Learn moreRelated posts
Microsoft Entra ID Governance: Azure subscription required to continue using guest governance features
Starting January 30, 2026, Microsoft Entra ID Governance requires tenants to link an Azure subscription to use guest governance features. With...
Azure Developer CLI (azd) – January 2026: Configuration & Performance
This post announces the January 2026 release of the Azure Developer CLI (`azd`). The post Azure Developer CLI (azd) – January 2026: Conf...
Azure SDK Release (January 2026)
Azure SDK releases every month. In this post, you'll find this month's highlights and release notes. The post Azure SDK Release (January 2026)...
Azure Cosmos DB TV Recap – From Burger to Bots – Agentic Apps with Cosmos DB and LangChain.js | Ep. 111
In Episode 111 of Azure Cosmos DB TV, host Mark Brown is joined by Yohan Lasorsa to explore how developers can build agent-powered application...
Accelerate Your Cosmos DB Infrastructure with GitHub Copilot CLI and Azure Cosmos DB Agent Kit
Modern infrastructure work is increasingly agent driven, but only if your AI actually understands the platform you’re deploying. This guide sh...
Accelerate Your Cosmos DB Infrastructure with GitHub Copilot CLI and Azure Cosmos DB Agent Kit
Modern infrastructure work is increasingly agent driven, but only if your AI actually understands the platform you’re deploying. This guide sh...
SharePoint: Migrate the Maps web part to Azure Maps
The SharePoint Maps web part will migrate from Bing Maps to Azure Maps starting March 2026, completing by mid-April. Key changes include renam...
Microsoft Azure Maia 200: Scott Guthrie EVP
Azure Cosmos DB TV Recap: Supercharging AI Agents with the Azure Cosmos DB MCP Toolkit (Ep. 110)
In Episode 110 of Azure Cosmos DB TV, host Mark Brown is joined by Sajeetharan Sinnathurai to explore how the Azure Cosmos DB MCP Toolkit is c...